In [18]:
import pandas as pd
import numpy as np 
import matplotlib.pyplot as plt
# import seaborn as sns 
import datetime
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
from plotly.graph_objs import Scatter, Figure, Layout
import plotly
import plotly.graph_objs as go
import plotly.express as px
from IPython.display import Markdown as md
init_notebook_mode(connected=False)
import io
import requests
import re

COVID-19 in Italy. Visuals


(alternatively, see results and code together here)

 


Data source: this GitHubi page

Authors and sources mentioned: Editore/Autore del dataset: Dipartimento della Protezione Civile. Categoria ISO 19115: Salute. Dati forniti dal Ministero della Salute.

Regional data files (Dati per Regione):
  • Struttura file giornaliero: dpc-covid19-ita-regioni-yyyymmdd.csv (dpc-covid19-ita-regioni-20200224.csv)
  • File complessivo: dpc-covid19-ita-regioni.csv
  • File ultimi dati (latest): dpc-covid19-ita-regioni-latest.csv

 

In [19]:
URL='https://it.wikipedia.org/wiki/Regione_(Italia)'
res=requests.get(URL)
tables=pd.read_html(res.text)
dt = tables[13]
In [20]:
def dewhite(x):
    ''.join(re.findall('\d+', x))

dt2 = dt[['Regione','Popolazione (ab.)']].copy()
dt2.columns = ['Region','Pop']
    
dt2.Pop = dt2.Pop.apply(lambda x: ''.join(re.findall('\d+', x))).astype(int)
In [21]:
s = requests.get("https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-regioni/dpc-covid19-ita-regioni.csv").content
dat = pd.read_csv(io.StringIO(s.decode('utf-8')))
cdate = dat.data.max()

md("Currently data as of date: {}".format(cdate))
Out[21]:

Currently data as of date: 2020-10-25T17:00:00


 

What's in the original dataframe?

In [22]:
md("All column names: {}".format(dat.columns.tolist()))
Out[22]:

All column names: ['data', 'stato', 'codice_regione', 'denominazione_regione', 'lat', 'long', 'ricoverati_con_sintomi', 'terapia_intensiva', 'totale_ospedalizzati', 'isolamento_domiciliare', 'totale_positivi', 'variazione_totale_positivi', 'nuovi_positivi', 'dimessi_guariti', 'deceduti', 'casi_da_sospetto_diagnostico', 'casi_da_screening', 'totale_casi', 'tamponi', 'casi_testati', 'note']

In [23]:
df = dat.drop(['stato','codice_regione'], axis=1)
df.columns = ['Date','Region','Lat','Long','HospWithSymptoms','IC','HospTotal','AtHome','CurrentlyPositive','VariationOfPositives','NewPositives','Recovered', 'Deaths','Diagnostico','Screening','TotalCases','NoOfTests','casi_testati','note']

df = pd.merge(df, dt2, left_on='Region', right_on='Region')

df['Date'] = pd.to_datetime(df['Date']).dt.date
df = df.set_index(df["Date"])
df.index = pd.to_datetime(df.index)

df['NewPositives'] = np.abs(df['NewPositives'])

dat.tail(5)
Out[23]:
data stato codice_regione denominazione_regione lat long ricoverati_con_sintomi terapia_intensiva totale_ospedalizzati isolamento_domiciliare ... variazione_totale_positivi nuovi_positivi dimessi_guariti deceduti casi_da_sospetto_diagnostico casi_da_screening totale_casi tamponi casi_testati note
5140 2020-10-25T17:00:00 ITA 19 Sicilia 38.115697 13.362357 642 95 737 9818 ... 666 695 5914 428 10855.0 6042.0 16897 642351 456572.0 NaN
5141 2020-10-25T17:00:00 ITA 9 Toscana 43.769231 11.255889 714 111 825 16495 ... 1632 1863 12708 1262 24763.0 6527.0 31290 1000835 671386.0 NaN
5142 2020-10-25T17:00:00 ITA 10 Umbria 43.106758 12.388247 215 29 244 4151 ... 374 463 2795 105 2575.0 4720.0 7295 277303 162084.0 NaN
5143 2020-10-25T17:00:00 ITA 2 Valle d'Aosta 45.737503 7.320149 63 2 65 1116 ... 88 97 1191 153 2265.0 260.0 2525 37826 24256.0 NaN
5144 2020-10-25T17:00:00 ITA 5 Veneto 45.434905 12.338452 585 71 656 16316 ... 1351 1468 25036 2329 24005.0 20332.0 44337 2238353 871568.0 NaN

5 rows × 21 columns


 

Variable names to English and their explanation

  • HospWithSymptoms : Currently hospitalized patients with symptoms
  • IC : Intensive care
  • HospTotal: Total number of currently hospitalized patients
  • AtHome : Currently at home confinement
  • CurrentlyPositive : Total amount of current positive cases (Hospitalised patients + Home confinement)
  • NewPositives : New amount of positive cases (Actual total amount of current positive cases - total amount of current positive cases of the previous day)
  • TotalCases : Total amount of positive cases
  • NoOfTests : Tests performed
In [24]:
df.tail()
Out[24]:
Date Region Lat Long HospWithSymptoms IC HospTotal AtHome CurrentlyPositive VariationOfPositives NewPositives Recovered Deaths Diagnostico Screening TotalCases NoOfTests casi_testati note Pop
Date
2020-10-21 2020-10-21 Veneto 45.434905 12.338452 439 56 495 10938 11433 1177 1422 24550 2282 23338.0 14927.0 38265 2178114 849385.0 NaN 4905854
2020-10-22 2020-10-22 Veneto 45.434905 12.338452 500 59 559 12049 12608 1175 1325 24681 2301 23515.0 16075.0 39590 2192554 854703.0 NaN 4905854
2020-10-23 2020-10-23 Veneto 45.434905 12.338452 515 64 579 13455 14034 1426 1550 24798 2308 23734.0 17406.0 41140 2208831 860733.0 NaN 4905854
2020-10-24 2020-10-24 Veneto 45.434905 12.338452 548 68 616 15005 15621 1587 1729 24931 2317 23881.0 18988.0 42869 2226292 866907.0 NaN 4905854
2020-10-25 2020-10-25 Veneto 45.434905 12.338452 585 71 656 16316 16972 1351 1468 25036 2329 24005.0 20332.0 44337 2238353 871568.0 NaN 4905854

 

daily numbers & moving averages (MA)

(double click and click on legend to select one or multiple regions in the graph)

In [25]:
df2 = df

fig = px.line(df2, x=df2.index, y="NewPositives", color="Region", hover_name="Region",
        render_mode="svg", log_y=False)
fig.update_layout(title="Daily new positive cases")
fig.show()
In [26]:
df2['MovAv7'] = df2['NewPositives'].rolling(window=7).mean()

fig = px.line(df2[df2.index>'2020-3-1'], x=df2.index[df2.index>'2020-3-1'], y="MovAv7", color="Region", hover_name="Region",
        render_mode="svg", log_y=False)
fig.update_layout(title="7-day MA of new positive cases")
fig.show()
In [37]:
df2['NewPos_per_100K'] = df2['NewPositives']/df2['Pop']*1000_00

df2['NewPos_per_100K'] = df2['NewPos_per_100K'].rolling(window=7).mean()

fig = px.line(df2[df2.index>'2020-3-1'], x=df2.index[df2.index>'2020-3-1'], y="NewPos_per_100K", color="Region", 
              hover_name="Region", log_y=False)
fig.update_layout(title="7-day MA of new positive cases, per 100K")
fig.show()
In [31]:
df2['IC_per_100K'] = df2['IC']/df2['Pop']*1000_00

fig = px.line(df2, x="Date", y="IC_per_100K", color="Region", hover_name="Region",
        render_mode="svg", log_y=False)
fig.update_layout(title="Current number of intensive care patients, per 100K")
fig.show()
In [32]:
df2['Hosp_per_100K'] = df2['HospTotal']/df2['Pop']*1000_00

fig = px.line(df2, x="Date", y="Hosp_per_100K", color="Region", hover_name="Region",
        render_mode="svg", log_y=False)
fig.update_layout(title="Current number of hospitalized, per 100K")
fig.show()
In [30]:
df3 = df2.copy()

df3['NewDeaths'] = df3['Deaths'] - df3.groupby(['Region'])['Deaths'].transform('shift')

fig = px.bar(df3, x=df3['Date'], y="NewDeaths", color="Region", hover_name="Date")
fig.update_layout(title="Daily number of deaths")
fig.show()
In [33]:
df2['Deaths_per_100K'] = (df2['Deaths']/df2['Pop'])*1000_00
fig = px.line(df2, x="Date", y="Deaths_per_100K", color="Region", 
              hover_name="Region", render_mode="svg", line_shape='spline')
fig.update_layout(title="Cumulative number of deaths, per 100K")
fig.show()
In [34]:
df2['Change_per_100K'] = df2['VariationOfPositives']/df2['Pop']*1000_00
df2['Change_per_100K'] = df2['Change_per_100K'].rolling(window=7).mean()

fig = px.line(df2[(df2.index>'2020-3-1') & (df2['Region']!="""Valle d'Aosta""")], x='Date', y="Change_per_100K", 
              color="Region", hover_name="Date")
fig.update_layout(title="7-day MA of change in current positive cases, per 100K (excl. Valle d'Aosta)")
fig.show()
In [35]:
df2['Current_per_100K'] = df2['CurrentlyPositive']/df2['Pop']*1000_00
df2['Current_per_100K'] = df2['Current_per_100K'].rolling(window=14).mean()

fig = px.line(df2[(df2.index>'2020-3-7')], x='Date', y="Current_per_100K", color="Region", hover_name="Date")
fig.update_layout(title="14-day MA of current positive cases, per 100K")
fig.show()

 

All regions together

In [36]:
df2 = df
df_sum = df2.drop(['Lat','Long'], axis=1).groupby(df.Date).sum().reset_index()

df_sum2 = pd.melt(df_sum, id_vars=['Date'], value_vars=['NewPositives','IC','HospTotal'])

fig = px.line(df_sum2, x="Date", y="value", color='variable', hover_name="value", render_mode="svg", log_y=True, 
              line_shape='spline')
fig.update_layout(title="Number of new positive cases, current IC patients and currently hospitalized")
fig.show()
In [ ]: